Yongkang Zhang

Identifiers

• name variant Yongkang Zhang 0.60 · backfill

Papers (4)

1. Reducing Credit Assignment Variance via Counterfactual Reasoning Paths cs.LG · 2026 · author #2
2. Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning cs.LG · 2026 · author #2
3. Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction cs.LG · 2026 · author #2
4. Design Conditions for Intra-Group Learning of Sequence-Level Rewards: Token Gradient Cancellation cs.LG · 2026 · author #2

Mentions

• 2605.05226 #2 · arxiv_oai · confidence 0.70 Yongkang Zhang
• 2604.17328 #2 · arxiv_oai · confidence 0.70 Yongkang Zhang
• 2604.13088 #2 · arxiv_oai · confidence 0.70 Yongkang Zhang
• 2605.16302 #2 · arxiv_oai · confidence 0.70 Yongkang Zhang

Frequent Coauthors

• Fei Ding 4 shared papers
• Zijian Zeng 4 shared papers
• Huiming Yang 2 shared papers
• Runhao Liu 2 shared papers
• Sibo Wang 2 shared papers
• youwei wang 2 shared papers
• Yuhao Liao 2 shared papers
• Guoxiong Zhou 1 shared papers
• Linglin Liao 1 shared papers
• Yeling Peng 1 shared papers